Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.20111 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909596637986816 |
|---|---|
| author | Jain, Anubhav Kobayashi, Yuya Murata, Naoki Takida, Yuhta Shibuya, Takashi Mitsufuji, Yuki Cohen, Niv Memon, Nasir Togelius, Julian |
| author_facet | Jain, Anubhav Kobayashi, Yuya Murata, Naoki Takida, Yuhta Shibuya, Takashi Mitsufuji, Yuki Cohen, Niv Memon, Nasir Togelius, Julian |
| contents | Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embed a secret key in the initial noise. The resulting pattern is often considered hard to remove and forge into unrelated images. In this paper, we propose a black-box adversarial attack without presuming access to the diffusion model weights. Our attack uses only a single watermarked example and is based on a simple observation: there is a many-to-one mapping between images and initial noises. There are regions in the clean image latent space pertaining to each watermark that get mapped to the same initial noise when inverted. Based on this intuition, we propose an adversarial attack to forge the watermark by introducing perturbations to the images such that we can enter the region of watermarked images. We show that we can also apply a similar approach for watermark removal by learning perturbations to exit this region. We report results on multiple watermarking schemes (Tree-Ring, RingID, WIND, and Gaussian Shading) across two diffusion models (SDv1.4 and SDv2.0). Our results demonstrate the effectiveness of the attack and expose vulnerabilities in the watermarking methods, motivating future research on improving them. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image Jain, Anubhav Kobayashi, Yuya Murata, Naoki Takida, Yuhta Shibuya, Takashi Mitsufuji, Yuki Cohen, Niv Memon, Nasir Togelius, Julian Computer Vision and Pattern Recognition Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embed a secret key in the initial noise. The resulting pattern is often considered hard to remove and forge into unrelated images. In this paper, we propose a black-box adversarial attack without presuming access to the diffusion model weights. Our attack uses only a single watermarked example and is based on a simple observation: there is a many-to-one mapping between images and initial noises. There are regions in the clean image latent space pertaining to each watermark that get mapped to the same initial noise when inverted. Based on this intuition, we propose an adversarial attack to forge the watermark by introducing perturbations to the images such that we can enter the region of watermarked images. We show that we can also apply a similar approach for watermark removal by learning perturbations to exit this region. We report results on multiple watermarking schemes (Tree-Ring, RingID, WIND, and Gaussian Shading) across two diffusion models (SDv1.4 and SDv2.0). Our results demonstrate the effectiveness of the attack and expose vulnerabilities in the watermarking methods, motivating future research on improving them. |
| title | Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.20111 |